Outliers


In statistics, outliers are data points that don’t belong to a certain population. It is an abnormal observation that lies far away from other values. An outlier is an observation that diverges from otherwise well-structured data.

For Example, you can clearly see the outlier in this list: [20,24,22,19,29,18,4300,30,18]

outliers1

Types of Outliers

  • Univariate

    • Univariate can be found when we looking at a distribution of values in single feature space

  • multivariate

    • multivariate outlier can be found in n dimensional space

Different flavours of outliers

  • Point (Single Data point Outlier)

  • Contextual (Noise in data)

  • Collective (subset of novelties in data)

Methods for outlier detection